Levent Sagun

Publication Activity (10 Years)

Years Active: 2015-2023
Publications (10 Years): 37

Top Topics

Stochastic Gradient Descent

Top Venues

ICLR (Workshop)

Publications

Samuel James Bell, Levent Sagun
Simplicity Bias Leads to Amplified Performance Disparities. FAccT (2023)
Arjun Subramonian, Adina Williams, Maximilian Nickel, Yizhou Sun, Levent Sagun
Weisfeiler and Lehman Go Measurement Modeling: Probing the Validity of the WL Test. CoRR (2023)
Vítor Albiero, Raghav Mehta, Ivan Evtimov, Samuel J. Bell, Levent Sagun, Aram Markosyan
Confusing Large Models by Confusing Small Models. ICCV (Workshops) (2023)
Arjun Subramonian, Levent Sagun, Yizhou Sun
Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction. CoRR (2023)
Priya Goyal, Adriana Romero-Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier
Fairness Indicators for Systematic Assessments of Visual Feature Extractors. FAccT (2022)
Priya Goyal, Quentin Duval, Isaac Seessel, Mathilde Caron, Ishan Misra, Levent Sagun, Armand Joulin, Piotr Bojanowski
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision. CoRR (2022)
Samuel J. Bell, Levent Sagun
Simplicity Bias Leads to Amplified Performance Disparities. CoRR (2022)
Berfin Simsek, Melissa Hall, Levent Sagun
Understanding out-of-distribution accuracies through quantifying difficulty of test samples. CoRR (2022)
Priya Goyal, Adriana Romero-Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier
Fairness Indicators for Systematic Assessments of Visual Feature Extractors. CoRR (2022)
David Lopez-Paz, Diane Bouchacourt, Levent Sagun, Nicolas Usunier
Measuring and signing fairness as performance under multiple stakeholder distributions. CoRR (2022)
Stéphane d'Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. ICML (2021)
Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli
On the interplay between data structure and loss function in classification problems. NeurIPS (2021)
Stéphane d'Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases. CoRR (2021)
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Ari Morcos
Transformed CNNs: recasting pre-trained convolutional layers with self-attention. CoRR (2021)
Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun, Giulio Biroli
More data or more parameters? Investigating the effect of data structure on generalization. CoRR (2021)
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
Triple descent and the two kinds of overfitting: Where & why do they appear? CoRR (2020)
Levent Sagun, Çaglar Gülçehre, Adriana Romero, Negar Rostemzadeh, Stefano Sarao Mannelli
Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver. CoRR (2020)
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
Triple descent and the two kinds of overfitting: where & why do they appear? NeurIPS (2020)
Mario Geiger, Arthur Jacot, Stefano Spigler, Franck Gabriel, Levent Sagun, Stéphane d'Ascoli, Giulio Biroli, Clément Hongler, Matthieu Wyart
Scaling description of generalization with number of parameters in deep learning. CoRR (2019)
Stéphane d'Ascoli, Levent Sagun, Joan Bruna, Giulio Biroli
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias. CoRR (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. CoRR (2019)
Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks. CoRR (2019)
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Joan Bruna
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias. NeurIPS (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. ICML (2019)
Stefano Spigler, Mario Geiger, Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Matthieu Wyart
A jamming transition from under- to over-parametrization affects loss landscape and generalization. CoRR (2018)
David Lopez-Paz, Levent Sagun
Easing non-convex optimization with neural networks. ICLR (Workshop) (2018)
Levent Sagun, Utku Evci, V. Ugur Güney, Yann N. Dauphin, Léon Bottou
Empirical Analysis of the Hessian of Over-Parametrized Neural Networks. ICLR (Workshop) (2018)
Marco Baity-Jesi, Levent Sagun, Mario Geiger, Stefano Spigler, Gérard Ben Arous, Chiara Cammarota, Yann LeCun, Matthieu Wyart, Giulio Biroli
Comparing Dynamics: Deep Neural Networks versus Glassy Systems. CoRR (2018)
Mario Geiger, Stefano Spigler, Stéphane d'Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, Matthieu Wyart
The jamming transition as a paradigm to understand the loss landscape of deep neural networks. CoRR (2018)
Marco Baity-Jesi, Levent Sagun, Mario Geiger, Stefano Spigler, Gérard Ben Arous, Chiara Cammarota, Yann LeCun, Matthieu Wyart, Giulio Biroli
Comparing Dynamics: Deep Neural Networks versus Glassy Systems. ICML (2018)
Matthew Dunn, Levent Sagun, Mike Higgins, V. Ugur Güney, Volkan Cirik, Kyunghyun Cho
SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine. CoRR (2017)
Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. ICLR (Poster) (2017)
Andrew J. Ballard, Ritankar Das, Stefano Martiniani, Dhagash Mehta, Levent Sagun, Jacob D. Stevenson, David J. Wales
Perspective: Energy Landscapes for Machine Learning. CoRR (2017)
Matthew Dunn, Levent Sagun, Hale Sirin, Daniel Chen
Early predictability of asylum court decisions. ICAIL (2017)
Levent Sagun, Utku Evci, V. Ugur Güney, Yann N. Dauphin, Léon Bottou
Empirical Analysis of the Hessian of Over-Parametrized Neural Networks. CoRR (2017)
Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. CoRR (2016)
Levent Sagun, Léon Bottou, Yann LeCun
Singularity of the Hessian in Deep Learning. CoRR (2016)
Levent Sagun, Thomas Trogdon, Yann LeCun
Universality in halting time and its applications in optimization. CoRR (2015)
Levent Sagun, V. Ugur Güney, Yann LeCun
Explorations on high dimensional landscapes. ICLR (Workshop) (2015)